Caveat verdict

pharma-ai

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Local molecular toxicity prediction and ADMET assessment using RDKit and scikit-learn; entirely local computation with no network access or credential use.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

10
security
80
transparency
80
maintenance

Findings (5)

Pattern match critical

Possible hardcoded credential

HEADLESS_LOGIN.md · code · TOKEN="ch_abc123def456

Pattern match high

References sudo — requests elevated privileges

HEADLESS_LOGIN.md · code · sudo

Pattern match high

apt-get install — installs system packages

HEADLESS_LOGIN.md · code · apt-get install

Pattern match medium

References child_process — can spawn system processes

src/python-bridge/index.ts · prose · downgraded · child_process

Pattern match medium

Uses spawn() — can execute external programs

src/python-bridge/index.ts · prose · downgraded · spawn(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API